© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 74878
    Prev
    Next
    INDEX
    Explanations

    references to the word "the" and related definitional terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gor
    -0.06
    dash
    -0.06
     bol
    -0.06
     Briggs
    -0.06
    -flat
    -0.05
     dash
    -0.05
    N
    -0.05
     disclaimer
    -0.05
     crc
    -0.05
     Bulg
    -0.05
    POSITIVE LOGITS
    iets
    0.08
    ,'#
    0.08
    коÑĤ
    0.07
    OUCH
    0.07
    igator
    0.07
     technology
    0.07
    inaire
    0.07
    rome
    0.07
    elik
    0.07
    ALER
    0.07
    Activations Density 0.029%

    No Known Activations